DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base

• URL: http://arxiv.org/abs/2507.14189v1
• Date: Mon, 14 Jul 2025 02:13:22 GMT
• Title: DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base
• Authors: Song Mao, Lejun Cheng, Pinlong Cai, Guohang Yan, Ding Wang, Botian Shi,
• Abstract summary: We introduce DeepWriter, a customizable, multimodal, long-form writing assistant that operates on a curated, offline knowledge base.<n>By deeply mining information from a structured corpus, DeepWriter generates coherent, factually grounded, and professional-grade documents.<n>Our experiments on financial report generation demonstrate that DeepWriter produces high-quality, verifiable articles.
• Score: 10.572896494190669
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in various applications. However, their use as writing assistants in specialized domains like finance, medicine, and law is often hampered by a lack of deep domain-specific knowledge and a tendency to hallucinate. Existing solutions, such as Retrieval-Augmented Generation (RAG), can suffer from inconsistency across multiple retrieval steps, while online search-based methods often degrade quality due to unreliable web content. To address these challenges, we introduce DeepWriter, a customizable, multimodal, long-form writing assistant that operates on a curated, offline knowledge base. DeepWriter leverages a novel pipeline that involves task decomposition, outline generation, multimodal retrieval, and section-by-section composition with reflection. By deeply mining information from a structured corpus and incorporating both textual and visual elements, DeepWriter generates coherent, factually grounded, and professional-grade documents. We also propose a hierarchical knowledge representation to enhance retrieval efficiency and accuracy. Our experiments on financial report generation demonstrate that DeepWriter produces high-quality, verifiable articles that surpasses existing baselines in factual accuracy and generated content quality.

Related papers

• Docopilot: Improving Multimodal Models for Document-Level Understanding [87.60020625241178]
  We present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents.<n>This dataset includes diverse document structures, extensive cross-page dependencies, and real question-answer pairs derived from the original documents.<n>Building on the dataset, we develop a native multimodal model, Docopilot, which can accurately handle document-level dependencies without relying on RAG.
  arXiv  Detail & Related papers  (2025-07-19T16:03:34Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• DeFine: A Decomposed and Fine-Grained Annotated Dataset for Long-form Article Generation [24.091769825963173]
  We introduce DeFine, a Decomposed and Fine-grained annotated dataset for long-form article generation.<n>DeFine is characterized by its hierarchical decomposition strategy and the integration of domain-specific knowledge with multi-level annotations.<n>The experimental results showed significant improvements in text quality, specifically in topic coverage, depth of information, and content fidelity.
  arXiv  Detail & Related papers  (2025-03-10T10:48:00Z)
• A Library Perspective on Supervised Text Processing in Digital Libraries: An Investigation in the Biomedical Domain [3.9519587827662397]
  We focus on relation extraction and text classification, using the showcase of eight biomedical benchmarks. We consider trade-offs between accuracy and application costs, dive into training data generation through distant supervision and large language models such as ChatGPT, LLama, and Olmo, and discuss how to design final pipelines.
  arXiv  Detail & Related papers  (2024-11-06T07:54:10Z)
• Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models [11.597314728459573]
  We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages. We propose STORM, a writing system for the Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking.
  arXiv  Detail & Related papers  (2024-02-22T01:20:17Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models [122.27878464009181]
  We conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available.
  arXiv  Detail & Related papers  (2023-05-13T11:28:37Z)
• Expository Text Generation: Imitate, Retrieve, Paraphrase [26.43857184008374]
  We propose the task of expository text generation, which seeks to automatically generate an accurate and stylistically consistent text for a topic. We develop IRP, a framework that overcomes the limitations of retrieval-augmented models and iteratively performs content planning, fact retrieval, and rephrasing. We show that IRP produces factual and organized expository texts that accurately inform readers.
  arXiv  Detail & Related papers  (2023-05-05T04:26:29Z)
• TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge [83.55215993730326]
  We propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework. Our model selects knowledge entries from two types of knowledge sources through dense retrieval and then injects them into the input encoding and output decoding stages respectively.
  arXiv  Detail & Related papers  (2022-03-16T10:37:59Z)
• Deep Latent-Variable Models for Text Generation [7.119436003155924]
  Deep neural network-based end-to-end architectures have been widely adopted. End-to-end approach conflates all sub-modules, which used to be designed by complex handcrafted rules, into a holistic encode-decode architecture. This dissertation presents how deep latent-variable models can improve over the standard encoder-decoder model for text generation.
  arXiv  Detail & Related papers  (2022-03-03T23:06:39Z)
• Letter-level Online Writer Identification [86.13203975836556]
  We focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues. A main challenge is that a person often writes a letter in different styles from time to time. We refer to this problem as the variance of online writing styles (Var-O-Styles)
  arXiv  Detail & Related papers  (2021-12-06T07:21:53Z)
• How to Train Your Agent to Read and Write [52.24605794920856]
  Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. It would be fascinating if we could train an intelligent agent to help people read and summarize papers, and perhaps even discover and exploit the potential knowledge clues to write novel papers. We propose a Deep ReAder-Writer (DRAW) network, which consists of a textitReader that can extract knowledge graphs (KGs) from input paragraphs and discover potential knowledge, a graph-to-text textitWriter that generates a novel paragraph, and a textit
  arXiv  Detail & Related papers  (2021-01-04T12:22:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.